Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    This neuron lights up on the leading words and key verbs of a question’s title (e.g. “Why,” “Is,” “Get rid of,” “Where to download,” etc.), effectively marking the start of a question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ?↵↵
    -0.07
    getFile
    -0.06
     Settings
    -0.06
     Executors
    -0.06
     spectacular
    -0.06
    ?↵↵
    -0.06
     FileUtils
    -0.06
     NOI
    -0.06
    volution
    -0.06
    !↵↵
    -0.06
    POSITIVE LOGITS
     hindsight
    0.07
     Ebola
    0.07
    qualified
    0.07
    阵
    0.06
    Execution
    0.06
     Ты
    0.06
     Пок
    0.06
     colorWithRed
    0.06
    ublik
    0.06
     running
    0.06
    Act Density 0.137%

    No Known Activations